An execution kernel that treats LLMs as untrusted compute and enforces policy via deterministic runtime interception.
-
Updated
Jan 4, 2026 - Python
An execution kernel that treats LLMs as untrusted compute and enforces policy via deterministic runtime interception.
Safe, auditable execution kernel for AI agent tools — DDD in Go, zero dependencies, with approval gates, execution budgets, evidence trails, and typed contracts.
Add a description, image, and links to the execution-kernel topic page so that developers can more easily learn about it.
To associate your repository with the execution-kernel topic, visit your repo's landing page and select "manage topics."